Evolving embodied intelligence from materials to machines

Agoston E. Eiben, David Howard, Danielle Frances Kennedy, Jean-Baptiste Mouret, Philip Valencia, Dave Winkler

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Natural lifeforms specialize to their environmental niches across many levels, from low-level features such as DNA and pro- teins, through to higher-level artefacts including eyes, limbs and overarching body plans. We propose ‘multi-level evolution’, a bottom-up automatic process that designs robots across multiple levels and niches them to tasks and environmental condi- tions. Multi-level evolution concurrently explores constituent molecular and material building blocks, as well as their possible assemblies into specialized morphological and sensorimotor configurations. Multi-level evolution provides a route to fully har- ness a recent explosion in available candidate materials and ongoing advances in rapid manufacturing processes. We outline a feasible architecture that realizes this vision, highlight the main roadblocks and how they may be overcome, and show robotic applications to which multi-level evolution is particularly suited. By forming a research agenda to stimulate discussion between researchers in related fields, we hope to inspire the pursuit of multi-level robotic design all the way from material to machine.
Original languageEnglish
Pages (from-to)12
Number of pages8
JournalNature Machine Intelligence
Volume1
Issue number1
Publication statusPublished - Jan 2019

Fingerprint

Robotics
Explosions
DNA
Robots
Proteins

Cite this

Eiben, A. E., Howard, D., Kennedy, D. F., Mouret, J-B., Valencia, P., & Winkler, D. (2019). Evolving embodied intelligence from materials to machines. Nature Machine Intelligence, 1(1), 12.
Eiben, Agoston E. ; Howard, David ; Kennedy, Danielle Frances ; Mouret, Jean-Baptiste ; Valencia, Philip ; Winkler, Dave. / Evolving embodied intelligence from materials to machines. In: Nature Machine Intelligence. 2019 ; Vol. 1, No. 1. pp. 12.
@article{4af2b099689c4dd8866045ee68fdc09d,
title = "Evolving embodied intelligence from materials to machines",
abstract = "Natural lifeforms specialize to their environmental niches across many levels, from low-level features such as DNA and pro- teins, through to higher-level artefacts including eyes, limbs and overarching body plans. We propose ‘multi-level evolution’, a bottom-up automatic process that designs robots across multiple levels and niches them to tasks and environmental condi- tions. Multi-level evolution concurrently explores constituent molecular and material building blocks, as well as their possible assemblies into specialized morphological and sensorimotor configurations. Multi-level evolution provides a route to fully har- ness a recent explosion in available candidate materials and ongoing advances in rapid manufacturing processes. We outline a feasible architecture that realizes this vision, highlight the main roadblocks and how they may be overcome, and show robotic applications to which multi-level evolution is particularly suited. By forming a research agenda to stimulate discussion between researchers in related fields, we hope to inspire the pursuit of multi-level robotic design all the way from material to machine.",
author = "Eiben, {Agoston E.} and David Howard and Kennedy, {Danielle Frances} and Jean-Baptiste Mouret and Philip Valencia and Dave Winkler",
year = "2019",
month = "1",
language = "English",
volume = "1",
pages = "12",
journal = "Nature Machine Intelligence",
issn = "2522-5839",
publisher = "Springer Nature",
number = "1",

}

Eiben, AE, Howard, D, Kennedy, DF, Mouret, J-B, Valencia, P & Winkler, D 2019, 'Evolving embodied intelligence from materials to machines' Nature Machine Intelligence, vol. 1, no. 1, pp. 12.

Evolving embodied intelligence from materials to machines. / Eiben, Agoston E.; Howard, David ; Kennedy, Danielle Frances; Mouret, Jean-Baptiste; Valencia, Philip; Winkler, Dave.

In: Nature Machine Intelligence, Vol. 1, No. 1, 01.2019, p. 12.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Evolving embodied intelligence from materials to machines

AU - Eiben, Agoston E.

AU - Howard, David

AU - Kennedy, Danielle Frances

AU - Mouret, Jean-Baptiste

AU - Valencia, Philip

AU - Winkler, Dave

PY - 2019/1

Y1 - 2019/1

N2 - Natural lifeforms specialize to their environmental niches across many levels, from low-level features such as DNA and pro- teins, through to higher-level artefacts including eyes, limbs and overarching body plans. We propose ‘multi-level evolution’, a bottom-up automatic process that designs robots across multiple levels and niches them to tasks and environmental condi- tions. Multi-level evolution concurrently explores constituent molecular and material building blocks, as well as their possible assemblies into specialized morphological and sensorimotor configurations. Multi-level evolution provides a route to fully har- ness a recent explosion in available candidate materials and ongoing advances in rapid manufacturing processes. We outline a feasible architecture that realizes this vision, highlight the main roadblocks and how they may be overcome, and show robotic applications to which multi-level evolution is particularly suited. By forming a research agenda to stimulate discussion between researchers in related fields, we hope to inspire the pursuit of multi-level robotic design all the way from material to machine.

AB - Natural lifeforms specialize to their environmental niches across many levels, from low-level features such as DNA and pro- teins, through to higher-level artefacts including eyes, limbs and overarching body plans. We propose ‘multi-level evolution’, a bottom-up automatic process that designs robots across multiple levels and niches them to tasks and environmental condi- tions. Multi-level evolution concurrently explores constituent molecular and material building blocks, as well as their possible assemblies into specialized morphological and sensorimotor configurations. Multi-level evolution provides a route to fully har- ness a recent explosion in available candidate materials and ongoing advances in rapid manufacturing processes. We outline a feasible architecture that realizes this vision, highlight the main roadblocks and how they may be overcome, and show robotic applications to which multi-level evolution is particularly suited. By forming a research agenda to stimulate discussion between researchers in related fields, we hope to inspire the pursuit of multi-level robotic design all the way from material to machine.

M3 - Article

VL - 1

SP - 12

JO - Nature Machine Intelligence

JF - Nature Machine Intelligence

SN - 2522-5839

IS - 1

ER -

Eiben AE, Howard D, Kennedy DF, Mouret J-B, Valencia P, Winkler D. Evolving embodied intelligence from materials to machines. Nature Machine Intelligence. 2019 Jan;1(1):12.